| 1 | Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention | Ales Kubicek, Andrea Caciolai, Liangzu Peng +7 | cs.AI | 2026-10-30 |
| 2 | RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory | Shengguang Wu, Suning Huang, Cherie Ho +3 | cs.RO | 2026-10-30 |
| 3 | Hyperbolic Inverse Reinforcement Learning | Iulia Rusu, Anoop Praturu, Sergei Gepshtein +1 | cs.LG | 2026-10-30 |
| #4 | REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control | Pengfei Zhou, Yixing Ma, Zhengfeiyang Zhang +5 | cs.RO | 2026-10-30 |
| #5 | Learning Clean Generative Processes from Noisy Measurements | Fabian Kruse, Lorenzo Baldassari, Ivan Dokmanić | cs.CV | 2026-10-30 |
| #6 | Asynchronous Flow Map Language Models | Chanhyuk Lee, Wonjung Kim, Patrick Pynadath +5 | cs.CL | 2026-10-30 |
| #7 | FoAViS: Analyzing Learned Fixation Strategies in a Foveated Active Vision System | Valentin Hassler, Jonathan Henrich, Yohaï-Eliel Berreby +2 | cs.CV | 2026-10-30 |
| #8 | When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity | Jun Liu, Dajie Sun, Zhenglun Kong +8 | cs.AI | 2026-10-30 |
| #9 | Learning Nonlocal Interactions in Large-Scale Heterogeneous Metamaterials through Scientific Machine Learning | Dex Doksoo Lee, Jehyeon Shin, Yue Yu +3 | cs.CE | 2026-10-30 |
| #10 | Text as an Index for Zero-Shot Cross-Domain Knowledge Tracing | Yin Yi, Haiping Ma, Siyu Song +2 | cs.CL | 2026-10-30 |
| #11 | DIFFNAS: Predictor-Free Neural Architecture Search via Diffusion Model and Zero-Cost Evaluation | Yize Sun, Hanzhang Ma, Zixin Wu +3 | cs.LG | 2026-10-30 |
| #12 | Towards Out-of-Distribution Uncertainty Quantification for Machine-Learned Interatomic Potentials via Pre-Training | Stefan P. Schmid, Tobias Setzer, Maximilian Scheurer | cs.LG | 2026-10-30 |
| #13 | Whose Values, Which Contexts, and What Signals? Grounding Cultural Value Alignment with Re3Culture | Jing Yao, Hyunjin Hwang, Weihua Zheng +12 | cs.AI | 2026-10-30 |
| #14 | Peeling the Matryoshka: Extracting Ontological Structure from Retrieval Embeddings | Eunchan Kim, Inwhee Joe | cs.CL | 2026-10-30 |
| #15 | Leveraging Quantum Measurement Randomness for Shot-Efficient Diffusion Models | Tianhao Guo, Dianxin Zheng, Yuhua Qian +4 | quant-ph | 2026-10-30 |
| #16 | UpLoop: Training Looped Transformers via Upcycling at No Extra Pretraining Compute | Cheng Liang, Tengfei Zhang, Ya Zhang +2 | cs.LG | 2026-10-30 |
| #17 | Hierarchical Residuals: A Minimalist Decoupling of Residual Width from Compute Width | Ziteng Wang, Jianqiao Lu, Xinyu Ma +4 | cs.LG | 2026-10-30 |
| #18 | Radial Kernel Attention for Long-Range Modeling in Polymer Machine Learning Force Fields | Wenbo Fu, Chenghui Mao, Chengwen Hu +2 | cs.AI | 2026-10-30 |
| #19 | $\nabla$Mimic: Ultra-Efficient Humanoid Control with Differentiable Simulation | Weyl Lu, Yubei Chen | cs.RO | 2026-10-30 |
| #20 | On the Generation Order in GFlowNets | Timofei Gritsaev, Evgeny Katasonov, Ildus Sadrtdinov +2 | cs.LG | 2026-10-30 |
| #21 | Risk-Sensitive Mission Planning for Multi-Target On-Orbit Inspection via Distributional Reinforcement Learning | Adam Abdin | cs.AI | 2026-10-30 |
| #22 | A Constructive Orbit-Based Theory of Learnability | Yunied Puig | cs.LG | 2026-10-30 |
| #23 | Chance-Constrained Inspection Viewpoint Sequencing for On-Orbit Servicing via Safe Reinforcement Learning | Chloé Carer, Adam Abdin | cs.AI | 2026-10-30 |
| #24 | Patch-Based Deep Kernel Learning for Data Assimilation and Bias Correction with Extremely Sparse Observations | Emanuele Mele, Angelo Coluccia, Massimo Cafaro +2 | cs.AI | 2026-10-30 |
| #25 | FOCUS: First-Order Control Using Optimal Transport Supervision for Imitation from Observations | João A. Cândido Ramos, Lionel Blondé, Hugues Vinzant +2 | cs.LG | 2026-10-30 |
| #26 | BDNet: Fast-slow thinking is all you need | Chenzhi Zheng, Zhuoran Zheng | cs.CV | 2026-10-30 |
| #27 | NormDetect: Anchored Calibration for Low-False-Positive Detection of Machine-Generated Web Text | Hanshuai Cui, Fanshuai Meng, Zhiqing Tang | cs.LG | 2026-10-30 |
| #28 | When Everyone Can Build a Model: Mechanistic Inference in the Age of AI | Marvin van Aalst, Adèle H. Ribeiro, Anna Matuszyńska | cs.LG | 2026-10-30 |
| #29 | Conditional Neural SDEs for Financial Time-Series Generation | Sina Molavipour, Alireza M. Javid, Björn Löfdahl +1 | stat.ML | 2026-10-30 |
| #30 | When Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing | Yixiang Luo, Ziheng Ma, Ke Chang +2 | cs.CR | 2026-10-30 |
| #31 | Online Evidence-Containment Prediction over Text Spans under Distinct Queries | Xiang Liu, Haochen Ding | cs.AI | 2026-10-30 |
| #32 | From prediction error to sparse events: Biologically inspired signed-dyadic coding for Mandarin keyword spotting | Zijian Zhou, Rui Liu, Rongxiang Nie +3 | cs.SD | 2026-10-30 |
| #33 | Task-Performance Routing for Multi-Teacher Distillation in CT Medical Image Segmentation | Jiaye Yang, Yao Liu, Die Dai +5 | cs.CV | 2026-10-30 |
| #34 | PRIN: A Perceptual-Structural Retinex-Inspired Network for Low-Light Image Enhancement | Qiyi Xie, Wei Chen Ng, Ziyao Li +4 | eess.IV | 2026-10-30 |
| #35 | Bayesian PET Reconstruction with Learned Flow Matching Priors via Langevin Sampling | Hengjia Ran, Huafeng Liu, Bo Zhao | eess.IV | 2026-10-30 |
| #36 | Transferring Peptide-Target Interaction Patterns to Small Molecules by Joint Guidance for Diffusion and Flow Matching | Jian Lee, Changyun Cho, Sun Kim | cs.LG | 2026-10-30 |
| #37 | ART of PIV: Agentic Real-Time Particle Image Velocimetry for Active Flow Control | Antonio Terpin, Francesco Banelli, Alan Bonomi +1 | physics.flu-dyn | 2026-10-30 |
| #38 | SPT-Flow: One Integration, Many Futures in Continuous-Time World Models | Mingyang Lyu, Yinqian Sun, Gongce Cao +5 | cs.LG | 2026-10-30 |
| #39 | RTL-Interact: Training EDA-Interactive Models for Multi-Task RTL Design | Wenxuan Shi, Yaoyu Zhu, Di Huang +13 | cs.AI | 2026-10-30 |
| #40 | A Positional Realizability Theory of Length Generalization in Single-Head Attention | Jiasong Han, Yunkai Chai, Jintao Wang | cs.LG | 2026-10-30 |
| #41 | Role-Aware Server Optimization for Multimodal Federated Learning with Missing Modalities | Liuyin Shi, Wenbo He | cs.LG | 2026-10-30 |
| #42 | Lifelong Learning of Scheduling Rules with Surrogate-assisted Genetic Programming for Dynamic Flexible Job Shop Scheduling | Luyao Zhu, Fangfang Zhang, Yi Mei +2 | cs.AI | 2026-10-30 |
| #43 | One Verdict Is Not Enough: Regression Testing Learned World Models and Their Test Harnesses | Junyu Huo, Zihao Wan, Ziqi Mao +1 | cs.SE | 2026-10-30 |
| #44 | An Empirical Study on Learning Rooftop Solar Potential from Satellite Imagery Directly Without Explicit Geometry | Joshua Lee | cs.CV | 2026-10-30 |
| #45 | Adaptive Scenario Generation for KL-DRO Around a Learned Density Model | Aron Brenner, Saurabh Amin | eess.SY | 2026-10-29 |
| #46 | Multi-View MoE: Letting Every Router Shape Expert Computation | Zelin Zhao, Tianchi Ma, Junyuan Shang +2 | cs.CL | 2026-10-29 |
| #47 | Retrieval as Traversal: Value-Indexed Memory for Stateful Long-Context Agents | Daniel Strauß, Zhenshan Bing, Alois Knoll | cs.AI | 2026-10-29 |
| #48 | A Low-Rank Space Captures Linear Alignment Between LLM and Human Neural Activity During Naturalistic Language Listening | Zach Paris, Emily Finn | cs.CL | 2026-10-29 |
| #49 | Numerical Integration on Bounded Domains via Learned Reflected Diffusions | Kirill Korolev, Artur Goldman, Timofei Gritsaev +2 | cs.LG | 2026-10-29 |
| #50 | Accurate MRI-free PET Quantification and Reliability Assessment via CT-to-MRI Synthesis and Conformal Prediction | Jungwoo Seo, Seung Yun Choi, Kun Ho Lee +3 | cs.CV | 2026-10-29 |